© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 2170
    Prev
    Next
    INDEX
    Explanations

    technical specifications and part numbers

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.69
    aluz
    -0.56
    URUS
    -0.53
    igshid
    -0.51
     Aran
    -0.48
    philis
    -0.47
    ControllerAdvice
    -0.47
    itatis
    -0.46
    InputTagHelper
    -0.46
    capulco
    -0.46
    POSITIVE LOGITS
     engines
    1.38
     engine
    1.35
     Engines
    1.18
    engine
    1.15
     Engine
    1.09
    engines
    1.03
     ENGINE
    1.01
    Engines
    0.94
    Engine
    0.93
    引擎
    0.88
    Activations Density 0.171%

    No Known Activations